Optimizing Reinforcement Learning Control Model in Furuta Pendulum and Transferring it to Real-World.
Myung Rae HongSanghun KangJingoo LeeSungchul SeoSeungyong HanJe-Sung KohDaeshik KangPublished in: IEEE Access (2023)
Keyphrases
- real world
- computational model
- probabilistic model
- parameter estimation
- wide range
- reinforcement learning
- high level
- data mining
- cost function
- em algorithm
- theoretical analysis
- theoretical framework
- statistical model
- control structure
- case study
- mobile robot
- neural network
- management system
- machine learning
- mathematical model